Loading blueprint versions...
Please wait while we gather all the unique runs for this blueprint.
Please wait while we gather all the unique runs for this blueprint.
Please wait while we prepare the detailed comparison.
DTEF: Predict response distributions for Bangladesh. Source: Global Dialogues GD1 (https://github.com/collect-intel/global-dialogues)
Average key point coverage extent for each model across all prompts.
| Prompts vs. Models | Claude 3.7 Sonnet | Claude Haiku 4.5 | Claude Sonnet 4 | Claude Sonnet 4.5 | Gemini 2.5 Flash | Gemma 3 12b It | Llama 4 Maverick | Mistral Large 2411 | Mistral Medium 3 | GPT 4.1 | GPT 4.1 Mini | GPT 4.1 Nano | GPT 4o | GPT 4o Mini | GPT 5 | GPT 5.1 | GPT OSS 120b | GPT OSS 20b | Qwen3 30b A3B Instruct 2507 | Qwen3 32b | Grok 4 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 9th 77.0% | 14th 75.0% | 11th 75.5% | 14th 75.0% | 11th 75.5% | 19th 73.3% | 6th 78.3% | 13th 75.3% | 18th 73.5% | 3rd 81.0% | 7th 78.0% | 21st 71.3% | 16th 74.8% | 17th 74.3% | 1st 81.5% | 7th 78.0% | 5th 78.5% | 20th 73.0% | 10th 76.5% | 4th 79.0% | 2nd 81.3% | |
| 59.0% | 65% | 61% | 53% | 59% | 51% | 47% | 51% | 62% | 46% | 64% | 65% | 64% | 63% | 66% | 62% | 56% | 59% | 52% | 54% | 80% | ||
| 74.8% | 81% | 80% | 81% | 82% | 72% | 78% | 81% | 63% | 65% | 69% | 82% | 69% | 69% | 61% | 79% | 77% | 75% | 75% | 81% | 72% | 79% | |
| 80.8% | 75% | 80% | 75% | 78% | 91% | 83% | 83% | 79% | 83% | 91% | 78% | 74% | 78% | 74% | 88% | 85% | 84% | 76% | 78% | 76% | 87% | |
| 90.2% | 87% | 79% | 93% | 81% | 88% | 85% | 98% | 97% | 100% | 100% | 87% | 78% | 89% | 96% | 97% | 94% | 96% | 89% | 93% | 89% | 79% |